Upload folder using huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-66b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 36864,
+  "hidden_size": 9216,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 72,
+  "num_hidden_layers": 64,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 9216
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.1"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f5b1e9bb0e81b4cc75d99e355559fdf7e583a6587881a2f9097513feccded1
+size 4362249920

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7aa5a0b7cc01fe478faae60940c626c2a70bb86db58daa2a30fcc85e7e930b
+size 4926767480

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2239962e84d043243f54d1d938bd6e95ea6a5648fc125aa8101478d6cafadc65
+size 4587047568

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7386820b30c3ca87d24c4cbc4fefbbc7eea1fdf25744ff77aa69228852811152
+size 4756897696

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4046f8890fe5757f4babfffe578261175c302cc17dd9bf75b4f5d8bdc1feafde
+size 4926767504

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f15e4a551523d3ce9d862e9742986cf637733e99d99323ac10d530717f4d3b4
+size 4587047608

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c770f7ca36a7e545d563dc4cfc57cdfcd634d38d6c0f7949cb20d08d624db091
+size 4756897728

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f7ab2a38c09b3a6d6e7638c426776d009d27180404f64b2f7d7d2fff378efd
+size 4926767520

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c326b7caa543a56eb805fe4bebfc6ffc8ded571929db7eb4e4da353b92eb5b43
+size 4587047608

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea4b562f56c5ad5ff6ba39c6d2555f9ae444696327975d084d2fb8d576d961d
+size 4756897728

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85711a384845af226756782882dca48918c4c0662fe7fb7736751a46f55006d5
+size 4926767520

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e7fac9ad93c6308fe7bd94630e368a4dc6d519159540434540fc9e49865f24
+size 4587047608

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be040ce137b298f7a1901fed6c3f87b68e43b1ef8c9e3ef26062477bc5dcfce
+size 4756897728

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfc6389d44ca8e0477d320965dc485372f393c97ccbd463269b5ad11b7d693b
+size 4926767520

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90a733056b9b59bc4990764ff5a69c228691dcf905661d46aa8b0ef8933ee95
+size 4587047608

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5daf50ce63680da75bfdcd7332c32c8d18181082efcf4a22927b135dc971e96
+size 4756897728

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb56e39880d6848fbb0d8dd80d142a3990a55eb26d2cfb7b1ecfac7326066525
+size 4926767520

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2be865831fa48797cd3b93ff3321db5a60b106ceb1ca3fa30d18f7801032af1
+size 4587047608

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3aedd29d925e76534eac704c3a026143151f2f973a87e253f72213566ae639
+size 4756897728

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c672673a7e19e87441907fbc7a368721bb3a3f1eb46ba158b392cc266c9acc4
+size 4926767520

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5660f3711650846f8abd1bf21bebb76a7697904a7a50cd5546654226740a67
+size 4587047608

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b40fa7c4350f6f293b9b6539a30006fcc45db820bc0ce5e843e61a853a9857
+size 4756897728

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73122f6bf20c3b960e090a52b760f5a972cc86626e7add9c197850c217392ce5
+size 4926767520

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db84d9e1ae1d30de33b418d3ecf492e482a876a99df214caba4a0ffd72033306
+size 4587047608

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8f7af6124aaf15f3139a1098212fdbfaa1b3adc7dcde10e5a4e16c0f76184e
+size 4756897728

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af11ac9476aa9473affa85e8e0a6ba1427abe0c1b7919a4ef79e6eefa4bbc474
+size 4926767520

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0521fddee068cce26658c620c30c5585749d4d4af33bbf920f1eff3b6791129f
+size 4587047608

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b7951e5af3b973422b0d94d2976d43bf5f94d252de0af47045b9884d907b3a
+size 3397757472

model.safetensors.index.json

@@ -0,0 +1,1035 @@
+{
+  "metadata": {
+    "total_size": 131439403008
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.final_layer_norm.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.final_layer_norm.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00028.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00006-of-00028.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00007-of-00028.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00009-of-00028.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00010-of-00028.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00012-of-00028.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00013-of-00028.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.32.fc1.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.fc1.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.fc2.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.fc2.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.final_layer_norm.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.final_layer_norm.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.k_proj.bias": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.out_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.out_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.q_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.v_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn_layer_norm.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.32.self_attn_layer_norm.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.fc1.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.fc1.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.fc2.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.fc2.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.final_layer_norm.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.final_layer_norm.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.k_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.out_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.out_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.q_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.v_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn_layer_norm.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.33.self_attn_layer_norm.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.fc1.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.fc1.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.fc2.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.fc2.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.final_layer_norm.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.final_layer_norm.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.k_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.out_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.out_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.q_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.v_proj.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn_layer_norm.bias": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.34.self_attn_layer_norm.weight": "model-00015-of-00028.safetensors",
+    "model.decoder.layers.35.fc1.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.fc1.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.fc2.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.fc2.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.final_layer_norm.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.final_layer_norm.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.k_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.out_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.out_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.q_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.v_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn_layer_norm.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.35.self_attn_layer_norm.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.fc1.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.fc1.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.fc2.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.36.fc2.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.36.final_layer_norm.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.36.final_layer_norm.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.k_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.out_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.out_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.q_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.v_proj.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn_layer_norm.bias": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.36.self_attn_layer_norm.weight": "model-00016-of-00028.safetensors",
+    "model.decoder.layers.37.fc1.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.fc1.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.fc2.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.fc2.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.final_layer_norm.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.final_layer_norm.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.k_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.out_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.out_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.q_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.v_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn_layer_norm.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.37.self_attn_layer_norm.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.fc1.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.fc1.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.fc2.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.fc2.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.final_layer_norm.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.final_layer_norm.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.k_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.out_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.out_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.q_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.v_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn_layer_norm.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.38.self_attn_layer_norm.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.39.fc1.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.fc1.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.fc2.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.fc2.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.final_layer_norm.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.final_layer_norm.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.k_proj.bias": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.out_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.out_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.q_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.v_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn_layer_norm.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.39.self_attn_layer_norm.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.40.fc1.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.fc1.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.fc2.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.fc2.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.final_layer_norm.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.final_layer_norm.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.k_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.out_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.out_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.q_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.v_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn_layer_norm.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.40.self_attn_layer_norm.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.fc1.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.fc1.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.fc2.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.fc2.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.final_layer_norm.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.final_layer_norm.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.k_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.out_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.out_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.q_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.v_proj.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn_layer_norm.bias": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.41.self_attn_layer_norm.weight": "model-00018-of-00028.safetensors",
+    "model.decoder.layers.42.fc1.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.fc1.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.fc2.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.fc2.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.final_layer_norm.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.final_layer_norm.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.k_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.out_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.out_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.q_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.v_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn_layer_norm.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.42.self_attn_layer_norm.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.fc1.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.fc1.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.fc2.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.43.fc2.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.43.final_layer_norm.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.43.final_layer_norm.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.k_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.out_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.out_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.q_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.v_proj.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn_layer_norm.bias": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.43.self_attn_layer_norm.weight": "model-00019-of-00028.safetensors",
+    "model.decoder.layers.44.fc1.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.fc1.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.fc2.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.fc2.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.final_layer_norm.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.final_layer_norm.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.k_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.out_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.out_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.q_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.v_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn_layer_norm.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.44.self_attn_layer_norm.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.fc1.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.fc1.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.fc2.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.fc2.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.final_layer_norm.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.final_layer_norm.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.k_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.out_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.out_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.q_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.v_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn_layer_norm.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.45.self_attn_layer_norm.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.46.fc1.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.fc1.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.fc2.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.fc2.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.final_layer_norm.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.final_layer_norm.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.k_proj.bias": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.out_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.out_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.q_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.v_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn_layer_norm.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.46.self_attn_layer_norm.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.fc1.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.fc1.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.fc2.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.fc2.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.final_layer_norm.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.final_layer_norm.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.k_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.out_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.out_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.q_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.v_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn_layer_norm.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.47.self_attn_layer_norm.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.fc1.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.fc1.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.fc2.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.fc2.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.final_layer_norm.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.final_layer_norm.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.k_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.out_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.out_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.q_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.v_proj.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn_layer_norm.bias": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.48.self_attn_layer_norm.weight": "model-00021-of-00028.safetensors",
+    "model.decoder.layers.49.fc1.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.fc1.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.fc2.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.fc2.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.final_layer_norm.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.final_layer_norm.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.k_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.out_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.out_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.q_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.v_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn_layer_norm.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.49.self_attn_layer_norm.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.50.fc1.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.fc1.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.fc2.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.50.fc2.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.50.final_layer_norm.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.50.final_layer_norm.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.k_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.out_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.out_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.q_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.v_proj.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn_layer_norm.bias": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.50.self_attn_layer_norm.weight": "model-00022-of-00028.safetensors",
+    "model.decoder.layers.51.fc1.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.fc1.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.fc2.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.fc2.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.final_layer_norm.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.final_layer_norm.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.k_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.out_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.out_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.q_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.v_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn_layer_norm.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.51.self_attn_layer_norm.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.fc1.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.fc1.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.fc2.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.fc2.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.final_layer_norm.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.final_layer_norm.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.k_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.out_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.out_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.q_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.v_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn_layer_norm.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.52.self_attn_layer_norm.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.53.fc1.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.fc1.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.fc2.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.fc2.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.final_layer_norm.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.final_layer_norm.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.k_proj.bias": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.out_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.out_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.q_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.v_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn_layer_norm.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.53.self_attn_layer_norm.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.fc1.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.fc1.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.fc2.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.fc2.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.final_layer_norm.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.final_layer_norm.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.k_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.out_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.out_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.q_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.v_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn_layer_norm.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.54.self_attn_layer_norm.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.fc1.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.fc1.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.fc2.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.fc2.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.final_layer_norm.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.final_layer_norm.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.k_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.out_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.out_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.q_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.v_proj.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn_layer_norm.bias": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.55.self_attn_layer_norm.weight": "model-00024-of-00028.safetensors",
+    "model.decoder.layers.56.fc1.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.fc1.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.fc2.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.fc2.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.final_layer_norm.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.final_layer_norm.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.k_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.out_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.out_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.q_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.v_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn_layer_norm.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.56.self_attn_layer_norm.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.fc1.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.fc1.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.fc2.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.57.fc2.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.57.final_layer_norm.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.57.final_layer_norm.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.k_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.out_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.out_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.q_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.v_proj.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn_layer_norm.bias": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.57.self_attn_layer_norm.weight": "model-00025-of-00028.safetensors",
+    "model.decoder.layers.58.fc1.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.fc1.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.fc2.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.fc2.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.final_layer_norm.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.final_layer_norm.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.k_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.out_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.out_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.q_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.v_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn_layer_norm.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.58.self_attn_layer_norm.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.fc1.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.fc1.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.fc2.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.fc2.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.final_layer_norm.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.final_layer_norm.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.k_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.out_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.out_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.q_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.v_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn_layer_norm.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.59.self_attn_layer_norm.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00003-of-00028.safetensors",
+    "model.decoder.layers.60.fc1.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.fc1.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.fc2.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.fc2.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.final_layer_norm.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.final_layer_norm.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.k_proj.bias": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.out_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.out_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.q_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.v_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn_layer_norm.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.60.self_attn_layer_norm.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.fc1.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.fc1.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.fc2.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.fc2.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.final_layer_norm.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.final_layer_norm.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.k_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.out_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.out_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.q_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.v_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn_layer_norm.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.61.self_attn_layer_norm.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.fc1.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.fc1.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.fc2.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.fc2.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.final_layer_norm.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.final_layer_norm.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.k_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.out_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.out_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.q_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.v_proj.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn_layer_norm.bias": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.62.self_attn_layer_norm.weight": "model-00027-of-00028.safetensors",
+    "model.decoder.layers.63.fc1.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.fc1.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.fc2.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.fc2.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.final_layer_norm.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.final_layer_norm.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.k_proj.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.out_proj.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.out_proj.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.q_proj.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.v_proj.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn_layer_norm.bias": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.63.self_attn_layer_norm.weight": "model-00028-of-00028.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00004-of-00028.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00005-of-00028.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00005-of-00028.safetensors"
+  }
+}